Taliban attack Farah City
At different points in time in 2018, the Taliban attacked two Afghan cities: Farah City and Ghazni City.1 2 Aside from rare event intrigue, what explains their timing? I use records of violent events3 collected by Afghanistan’s Ministry of Interior to probe for answers. In this notebook, I examine the data, simplify its interpretation through aggregate statistics, and use these statistics to visualize the distribution of the threat in the country.
Attacks on Afghan cities occurred in provinces facing high threat,4 meaning the attacks occurred exclusively in provinces that experience more violent events than roughly 25 of the 34 provinces. The primary implication that we can draw from this finding is that a closer look at violent events within, not across provinces, could tell us a lot more about these rare events.
Ghazni had roughly 300 more violent events than the average of high threat provinces and over 3 times more violent events than the country average. Ghazni also had 370 more violent event incidents than Farah, which is a difference of more than one standard deviation. This means that Ghazni had a sizable nonsystematic component contributing to its level of violent events.
Farah’s violent events level was slightly below the high threat average, but was over 2 times greater than the average province.
We can see that the dataset is mostly complete in terms of events but is notably incomplete in terms of casualty information.
| Statistic | N | Mean | St. Dev. | Min | Pctl(25) | Pctl(75) | Max |
| Tracking.Number | 10,992 | 38,601.650 | 3,174.120 | 33,138 | 35,844.8 | 41,349.2 | 44,110 |
| Day | 10,992 | 15.422 | 8.779 | 1 | 8 | 23 | 31 |
| Latitude | 10,992 | 33.975 | 1.515 | 29.433 | 32.745 | 34.871 | 38.409 |
| Longitude | 10,992 | 67.266 | 2.684 | 61.058 | 64.900 | 69.254 | 71.599 |
| KIA.CIV.NGO.ASG | 604 | 3.851 | 8.304 | 1.000 | 1.000 | 3.000 | 103.000 |
| ABD.CIV.NGO.ASG | 49 | 9.204 | 25.375 | 1.000 | 1.000 | 5.000 | 170.000 |
| KIA | 1,960 | 3.030 | 4.116 | 1.000 | 1.000 | 3.000 | 45.000 |
| WIA | 2,463 | 2.620 | 3.151 | 1.000 | 1.000 | 3.000 | 70.000 |
| ABD.Report.Host.Nation.Security.Military | 80 | 3.737 | 4.215 | 1.000 | 1.000 | 5.000 | 25.000 |
| KIA.Report.Host.Nation.Government | 35 | 1.229 | 0.547 | 1.000 | 1.000 | 1.000 | 3.000 |
| WIA.Report.Host.Nation.Government | 19 | 1.789 | 1.182 | 1.000 | 1.000 | 2.000 | 5.000 |
| ABD.Report.Host.Nation.Government | 6 | 22.167 | 50.384 | 1.000 | 1.000 | 2.750 | 125.000 |
| KIA.Enemy..VEO.Insurgent.Criminal. | 2,421 | 9.178 | 13.191 | 1.000 | 2.000 | 11.000 | 300.000 |
| WIA.Enemy..VEO.Insurgent.Criminal. | 1,071 | 6.870 | 7.779 | 1.000 | 2.000 | 9.000 | 82.000 |
| DET.Enemy..VEO.Insurgent.Criminal. | 197 | 5.299 | 7.175 | 1.000 | 1.000 | 6.000 | 50.000 |
The barplot below shows some clustering in values, suggesting that we can further classify our provinces into easy to understand threat categories like: low, moderate, and high. Percentiles is a good solution.
With the below categories specified, the barplot is presented again in slightly different fashion. We can see that the use of percentiles does a fairly good job of classifying provinces into simplified threat categories.
\[\text{Province Threat} = \begin{cases} \text{high threat:} \hspace{1.5cm} \text{violent events} > 75\% \\ \text{moderate threat:} \hspace{.7cm} 25\% > \text{violent events} < 75\% \\ \text{low threat:} \hspace{1.7cm} \text{violent events} < 25\% \\ \end{cases} \]
While the barplots are interesting, they offer little insight into whether or not there is a geospatial component to the data. The map below fixes that. We can see that there is a substantive difference in the levels of violent of events depending on where you live in the country, with the south having the most violent events.
https://www.nytimes.com/2018/05/16/world/asia/taliban-farah-afghanistan.html↩
This includes government actions, insurgent actions, and explosions.↩
High threat provinces were determined by separating the violence levels of provinces into percentiles, with high threat provinces falling into the 75%. This means that 75% of all provinces have fewer violent events than high threat provinces.↩